Nature Explorer

Google Inc
Nature
Plants
Insects
Birds
Supported Device
Vision Kit

Nature explorer has 3 machine learning models based on MobileNet, trained on photos contributed by the iNaturalist community. These models are built to recognize 4,080 different species (~960 birds, ~1020 insects, ~2100 plants).

The species and images are a subset of the iNaturalist 2017 Competition dataset, organized by Visipedia.

In collaboration with iNaturalist

Already included in the most recent SD card image.
If you are using a version of the SD card image older than 2018-04-16, you will need to update it.

Download

Demo: Nature explorer

Time: 20 minutes

This demo lets you try 3 nature explorer models which can detect plants, insects, birds by using an image and seeing if the model can detect and identify them. The model can detect over ~4,080 different species, so we encourage you to try all sorts of images.

What you’ll need

Assembled Vision Kit (with latest SD card image)

Step 1: Get connected

First, make sure you’re connected to your device and have a terminal open. Otherwise you can’t tell your kit to start the demo.

Step 2: Stop your current demo

Your Vision Kit may already have another demo running, like the Smile Detector, which runs by default when your kit is turned on. You’ll need to turn off any demos that are currently running. To do that, press Control-C.

Step 3: Run the demo

Start with one of the following demos. If you would like to switch to the next demo, please stop the running demo first by pressing Control-C.

To run the plant classifier:

Enter the following command into your terminal application:

~/AIY-projects-python/src/examples/vision/mobilenet_based_classifier.py \
  --model_path ~/models/mobilenet_v2_192res_1.0_inat_plant.binaryproto \
  --label_path ~/models/mobilenet_v2_192res_1.0_inat_plant_labels.txt \
  --input_height 192 \
  --input_width 192 \
  --input_layer map/TensorArrayStack/TensorArrayGatherV3 \
  --output_layer prediction \
  --preview

To run the insect classifier:

Enter the following command into your terminal application:

~/AIY-projects-python/src/examples/vision/mobilenet_based_classifier.py \
  --model_path ~/models/mobilenet_v2_192res_1.0_inat_insect.binaryproto \
  --label_path ~/models/mobilenet_v2_192res_1.0_inat_insect_labels.txt \
  --input_height 192 \
  --input_width 192 \
  --input_layer map/TensorArrayStack/TensorArrayGatherV3 \
  --output_layer prediction \
  --preview

To run the bird classifier:

Enter the following command into your terminal application:

~/AIY-projects-python/src/examples/vision/mobilenet_based_classifier.py \
  --model_path ~/models/mobilenet_v2_192res_1.0_inat_bird.binaryproto \
  --label_path ~/models/mobilenet_v2_192res_1.0_inat_bird_labels.txt \
  --input_height 192 \
  --input_width 192 \
  --input_layer map/TensorArrayStack/TensorArrayGatherV3 \
  --output_layer prediction \
  --preview
Step 4: Point your Vision Kit to a plant, insect or bird

Terminal will show what is detected. Meanwhile, if you have a display connected, the demo will overlay detected object on top of the preview.

If you ran into an error, check Help.

Cleanup time

When you’re done with the demo, remember to stop it before trying another demo by pressing Control-C.